Equipment Data Development Case Study – Bayesian Weibull ... - Bayesian... · Equipment Data...
Transcript of Equipment Data Development Case Study – Bayesian Weibull ... - Bayesian... · Equipment Data...
Equipment Data Development Case Study – Bayesian Weibull Analysis
Wei Yu
Graduate Program in Operations Research and Industrial Engineering The University of Texas at Austin, Austin, TX 78712
Joint research with South Texas Project Nuclear Operating Company
Academic Advisor: Elmira Popova South Texas Project Advisors: Ernie Kee, Alice Sun
Summary This paper describes a statistical study done on a set of equipment failure data from the South Texas Project site. The main assumption in the existing methodology is that the time between failures is distributed as exponential random variable (i.e. constant failure rate) with random parameter that follows Lognormal prior distribution. In addition, the current data collection gathers only the number of failures in a given time period which is sufficient for the estimation procedure due to the exponential failure time assumption. The current study proposes to substitute the constant failure rate with time varying one by modeling the time between failures as Weibull random variable. This requires that we have a different set of failure observations – the actual time between failures rather than the number of failures only. The previous categorization defines unique groups based on their TPNS number and failure mode code. We created three sets of data based on three different grouping rules: functional, TPNS codes, TPNS codes and failure modes (the last one is the currently used grouping rule). Due to the detailed nature of the last category, the data set consists of 142 different groups, 135 of which have less than 8 data points. We present our analysis for all three data sets but should point out that more data are needed to reach statistically sound conclusions for the third grouping. Main accomplishments:
• Setup database of time between failures using plant specific observations only (in SAS)
• Performed goodness-of-fit and graphical data analysis to test the Weibull distribution assumption (in SAS)
• Analyzed a set of prior distributions for the Weibull parameters (in SAS) • Construct an algorithm to compute the posterior distributions and wrote an Excel
add-in to implement it.
407
Conclusions: • The Weibull assumption is statistically justified for the first data set where the
grouping leads to more than 30 data points per group • For the second data set we need more data to reach a final conclusion. The
participation of the rest of the power plants to a common database of failure data is crucial for this task.
• The new prior distributions on both parameters allow for higher modeling flexibility and better forecast of the failure rates.
Table of Contents
I. Data Preparation and Description
1. Initial data sets
2. Data preparation
3. Creating groups of data
1. Groups based on functional commonalities
2. Groups based on code assignment and failure modes
II. Descriptive Data Analysis
III. Bayesian analysis
IV. Appendix
408
I. Data preparation and description
1. Initial data sets: The following Excel files were provided:
• U1 equipment failure before 1103 (with 187 records)
• U2 equipment failure before 1103 (with 116 records)
• 12-03 equipment loss (with 17 records)
• 1-04 equipment loss (with 31 records)
• 2-04 equipment loss (with 48 records)
All files have similar structure. Table 1 gives the names of the columns for the first two
files (U1 equipment failure before 1103 and U2 equipment failure before 1103) and one
representative record. Table 2 contains the column definitions and one record for file 12-
03 equipment loss. Table 3 contains the column definitions and one record for files 1-04
equipment loss and 2-04 equipment loss.
We combined the above files using the TPNS variable as a primary key. The first data set
(Excel file data1.xls) contains the columns TPNS and Created TS.
2. Data Preparation
Bellow is a list of steps that we took in preparation of the data set called data2.xls:
• Sort the data using TPNS as a key.
• Transfer the Created TS to a new variable that represents the interval time
between two failure times for the specific component. We want to measure the
days between two failure times. In SAS, which is a statistical software package,
each observation of Created TS will transfer into a number for the days to a
system specific date. (In SAS, the default specific date is 1/1/1960). Since we
want the interval days, the actual default specific date is not important. We
created a new variable called date. It stands for the number of days between
Created TS and the specific date.
• We exported the data to a second file, data2.xls.
• Count the number of observations per TPNS: we found that we have less than 6
data points for each group, not enough to perform analysis.
409
3. Creating groups of data
In what follows, we describe two procedures for grouping of the data.
3.1 Groups based on functional commonalities
We followed simple rules to produce the data file called data3.xls.
• If the first character of TPNS is number, like 7S131TFW0190 stands for U1,
7S132TFW0190 stands for U2, we treated them as the same component.
• If the TPNSs only differ at the last several characters, such as N1FWFV7109,
N1FWFV7151, N1FWFV7152 and N1FWFV7153, we treated them at the same
group.
• If the TPNSs begin with letter, the second is number, for example, one is
N1FWFV7178, the other is N2FWFV7178, and we treated them as the same
component.
• Based on above, we got the file data3.xls. Table 4 gives an example of a group.
• We extracted the groups with more than 8 data points to perform the statistical
analysis also described in data3.xls.
The exact data that belong to each separate group are in Appendix, part II, Tables 1 - 11.
There are total of 11 different groups.
3.2 Groups based on code assignment and failure modes
This is the currently used grouping model, by different codes and failure modes. To be
consistent with it we created a data set following these rules. The resulting file is
data6.xls. Since there are large number of code and failure modes combinations many
groups contained less than 5 data points. One example from data5 is shown in Table 6.
There are 6 groups with more than 8 data points, listed in the Appendix, part III, Tables 1
- 6.
410
II. Descriptive data analysis For each group of data we performed the following set of statistical procedures:
• Descriptive statistics – number of data points, mean, standard deviation, skewness, and kurtosis.
• Relative frequency histogram – to assess the shape of the distribution
• Weibull probability plot – graphical assessment of the Weibull assumption
• Kolmogorov-Smirnov test – goodness-of-fit test for the Weibull distribution :
The Kolmogorov-Smirnov (K-S) test is based on the empirical distribution function constructed from the observed failure data. Given N ordered data points Y1, Y2, ..., YN, the ECDF is defined as
where n(i) is the number of points less than Yi, and Yi are ordered from the smallest to the largest value. It is a step function that increases by 1/N. Bellow if the definition of the null and research hypotheses for the Kolmogorov-Smirnov test: H0: The observed data come from a Weibull distribution Ha: The observed data do not come from the Weibull distribution
Test Statistic: The Kolmogorov-Smirnov test statistic is defined as
where F is the Weibull distribution function.
The descriptive analysis is done using the SAS statistical package.
411
1. Results for functional grouping
The table bellow shows the descriptive statistics for the 11 groups:
Group # data Points Mean St.Deviation Skewness Kurtosis 1. 18 19.667 32.711 2.747 8.404 2. 21 12.714 17.407 2.765 9.280 3. 9 41.222 55.816 2.196 5.285 4. 24 150.375 189.614 1.512 1.282 5. 38 117.632 124.584 2.764 9.906 6. 7 49.857 22.579 -.687 -.568 7. 37 10.027 10.797 2.843 10.462 8. 14 287.786 603.457 3.468 12.494 9. 18 18.278 17.364 2.066 5.07 10 18 58.944 61.681 .242 -2.167 11 26 19 26.127 1.86 2.4
If we assume that the data come from Weibull distribution with parameters and then the Kolmogorov-Smirnov test should yield high p-values (usually greater than 0.5). The table bellow shows the output from the test for all 11 groups and the maximum likelihood estimators for and .
α β
α β
Group P-Value α β 1 .685 14.04 .66 2 .5108 11.39 .8332 3 .9987 34.65 .7536 4 .1458 128.0 .7677 5 .3867 121.0 1.069 6 .8173 55.98 2.63 7 .5864 10.44 1.099 8 .3443 148.4 .4987 9 .539 19.68 1.222 10 .0587 46.27 .6787 11 .4345 16.03 .7726
The Weibull assumption is statistically justified for Groups 1, 2, 3, 6, 7, 9, and 11. For all 11 groups we built the relative frequency histograms and Weibull probability plots. The resulting graphs are in the Appendix, part IV, figure 1 – 11, part V, figure 1-11. We can safely conclude that for the grouping based on functional commonalities, the Weibull distribution is a good fit.
412
2. Results for grouping based on code and failure mode Out of the 142 groups that resulted from this rule we chose 6 (since they have more than 8 data points) for the analysis. They are defined in this table:
GROUP CODE # DATA POINTS AOV-LE-C 451 8 TKP-LE-C 455 18
XVM-LE-W 92 6 CAV-LE-W 95 11 CAV-LE-W 96 9 MDP-LE-C 127 10
As with the previous grouping rule, the results from the descriptive analysis and goodness-of-fit test for the Weibull distribution are given in the following two tables: Groups Code No. of
data points
Mean Standard Deviation
Skewness kurtosis
AOV-LE-C
451 8 350.491 528.964 2.497 6.567
TKP-LE-C
455 18 183.410 190.698 1.192 .982
XVM-LE-W
92 6 35.583 37.504 1.317 1.545
CAV-LE-W
95 11 17.525 40.177 3.234 10.57
CAV-LE-W
96 9 25.141 54.803 2.672 7.288
MDP-LE-C
127 10 34.332 42.095 1.985 4.187
Groups P-Value α β
1 .7015 26.21 .9368 2 .4967 13.64 .6061 3 .4547 24.65 .9364
4 .5923 168.9 .7905 5 .9534 53.33 2.359 6 .6277 503.2 .8392
413
III. Bayesian analysis The main difference between classical and Bayesian estimation is the assumption about the parameters of the proposed sampling distribution. The classical approach assumes that the parameters are unknown but constant, whereas the Bayesian regards them as random variables (with specified prior distributions). We will assume that the sampling distribution is Weibull with parameters and . Its density function equals to
λ β
0,,0),exp(),;( 1 >≥−= − βλλλββλ ββ ttttf If we have items, of which have failed at ordered times , and have operated without failing. If there are no withdrawals then we denote as
n s sTTT ,...,, 21 )( sn −
βω snT= - it is a sufficient statistic for estimating (also known as the rescaled total time on test).
λ
Case 1: is fixed, has gamma prior distribution with hyper-parameters and density function
β λ 00 , βα
00
0
/1
000,0 )(
1);( βλαα λ
βαβαλ −−
Γ= eg
Then the posterior mean of given the observed failure data is λ
1)(
),;|(0
000,0 +
+=
ws
swEβ
αββαλ .
Case 2: Inverted gamma prior distribution on ; uniform prior distribution on λθ /1= β Assume that has an inverted gamma prior distribution with hyper-parameters θ 00 , µν , and has uniform prior distribution with hyper-parameters . Denote by the observed failure information. Then the Bayesian point estimation for θ is given by
β 00 , βα z
],)1/[()|( 102 JvsJzE −+=θ where
βββ
α
β
dw
vJ vs
s
][0
0 0 11
2 ∫ −+= ,
βββ
α
β
dw
vJ vs
s
][0
0 01
1 ∫ += ,
i
s
iTv
1=∏= ,
01 µω += snT
The Bayesian point estimator for β becomes
ββββ
α
β
dw
vwhereJJJzE vs
s
][,/)|( 0
0 01
1
313 ∫ +
+
==
414
The integrals do not have closed form solution and thus the Bayesian estimates must be computed by numerical integration techniques. Bellow are the results for the code and failure mode grouping using both updating procedures. Groups Bayesian update
estimate * λBayesian update estimate ** (days)
λθ /1=
Bayesian update estimate ** (/hour)
λBayesian update estimate β **
AOV-LE-C 2.49E-05 2.40E+03 1.74E-05 8.73E-01 TKP-LE-C 1.11E-05 4222.038 9.87E-06 8.88E-01
XVM-LE-W 3.756E-07 132436.8 3.15E-07 8.64E-01
CAV-LE-W 6.803E-07 67319.79 6.19E-07 8.71E-01 CAV-LE-W 5.584E-07 83805.64 4.97E-07 8.64E-01 MDP-LE-C 6.193E-05 800.451 5.21E-05 8.72E-01
Note: *: λ is the Bayesian update estimate of failure rate; the prior distribution is Gamma; **: Θ, λ and β are the Bayesian update estimates of mean failure time, failure rate and shape; the prior for Θ is Inverted Gamma and β is Uniform (0.2, 0.9). The choice of the hyper-parameters values is not random. We used the values given in the DOE database for the values of the inverted gamma parameters, and empirically assessed the parameters of the uniform distribution.
415
IV. Appendix
I. Data tables: A. Basic tables:
Ct 192
Computed 1
CR/WO 03-11068
Date 7/19/2003
Activity No 432385
Wan Seq No 256316
Description WHILE ATTEMPTING TO OPEN 1D FWIV, THE MOTOR DRIVEN PUMPS
WOULD NOT RUN. DURING THE OPEN ATTEMPT, THE AIR DRIVEN
PUMPS RAN, BUT THE MOTOR DRIVEN PUMPS DID NOT. THE ONLY
NON-COMMON ITEM IN THE PUMP RUN CIRCUITS IS A CONTACT
WHICH SHOULD CLOSE ON LOW PRESSUR
Wmsy System FW
TPNS 7S131MPA011
Failure Mode Fails to run
Event Code 3A5- FAILED TO OPEN/FAILED IN CLOSED POSITION
Created TS 7/19/2003 5:17:57 PM
Tpns Unit 1
Actl Start Date 7/20/2003
Actl Finish Date 7/20/2003
Failure_Mode MDP-FR-C
Table 1
416
Ct 1.
Computed 1.
CR/WO 03-18222 N-D-M 12/11/03
Activity No
Wan Seq No
Description NOTICED A SLOW DRIP AND SMALL PUDDLE IN THE TURBINE
GENERATOR BUILDING WHILE CLEANING FOR PRIDE DAY. THE DRIP
WAS COMING FROM 1FW0193 - 7S131TF0193 - LOW POWER FEEDWATER
VALVE FROM A 1 1/4" PIPE CAP.
Wmsy System FW
TPNS 7S131TFW0193
Failure Mode XVM-LE-W
Event Code 4M- TOOL POUCH MAINTENANCE
Created TS 12/11/03 10:33 AM
Tpns Unit 1
Table 2
417
Ct 1.
Computed 1.
CR/WO 04-194 N-D-M 01/06/04
Activity No
Wan Seq No
Description STEAM GENERATOR 2C LO POWER FEED REG VALVE OUTLET
ISOLATION, 7S132TFW0190, HAS A PACKING LEAK. WATER AND
STEAM ARE BUBBLING UP AROUND THE STEM AFTER CLOSING THE
VALVE.
Wmsy System FW
TPNS 7S132TFW0190
Failure mode XVM-LE-W
Event Code 3C1W- WATER LEAK
Created TS 01/06/04 04:28 AM
Tpns Unit 2
Actl Start Date
Actl Finish Date
Table 3
TPNS CreatedTS date time time3
7T081MPA001A 4/5/2003 15800 21 1
7T081MPA1803 4/26/2003 15821 59 2
7T082MPA1803 4/26/2003 15821 59 9
7T082MPA001B 6/24/2003 15880 30 12
7T081MPA001A 7/24/2003 15910 2 21
7T081MPA001A 7/26/2003 15912 12 30
7T082MPA1803 8/7/2003 15924 1 59
7T081MPA001A 8/8/2003 15925 9 59
7T082MPA1803 8/17/2003 15934 178 178
7T081MPA001A 2/11/2004 16112
7T081MPA001A 2/11/2004 16112
Table 4
418
TPNS TS code date time
7S131MPA011 4/14/2003 127 15809 2
7S131MPA011 4/14/2003 127 15809 2
7S131MPA008 4/16/2003 127 15811 30
7S131MPA010 5/16/2003 127 15841 64
7S131MPA011 7/19/2003 127 15905 8
7S131MPA008 7/27/2003 127 15913 1
7S131MPA011 7/27/2003 127 15913 1
7S131MPA010 7/28/2003 127 15914 1
7S131MPA008 7/29/2003 127 15915 1
7S131MPA008 7/30/2003 127 15916 1
7S131MPA011 8/13/2003 127 15930 14
7S131MPA008 8/16/2003 127 15933 3
7S131MPA010 8/16/2003 127 15933 31
7S131MPA010 9/16/2003 127 15964 22
7S131MPA011 10/8/2003 127 15986 138
7S131MPA008 2/23/2004 127 16124
Table 5
TPNS CreatedTS FailureModes Code 7S131MPA008 4/16/2003 14:12 MDP-LE-C 127 7S131MPA008 7/29/2003 3:24 MDP-LE-C 127 7S131MPA008 8/16/2003 22:41 MDP-LE-C 127 7S131MPA010 5/16/2003 13:42 MDP-LE-C 127 7S131MPA010 7/28/2003 10:18 MDP-LE-C 127 7S131MPA010 8/16/2003 22:44 MDP-LE-C 127 7S131MPA010 9/16/2003 9:53 MDP-LE-C 127 7S131MPA011 10/8/2003 12:47 MDP-LE-C 127 7S131MPA011 8/13/2003 5:42 MDP-LE-C 127 7S131MPA011 7/27/2003 3:46 MDP-LE-C 127 7S131MPA008 02/23/04 10:00 PM MDP-LE-C 127 7S131MPA008 7/27/2003 3:38 MDP-NS-C 127 7S131MPA008 7/30/2003 1:58 MDP-NS-C 127 7S131MPA011 4/14/2003 18:30 MDP-NS-C 127 7S131MPA011 4/14/2003 18:30 MDP-NS-C 127
Table 6
419
II. Data tables for Functional grouping
TPNS CreatedTS date time Group 1
(Sorted time) 7S132MPA009 4/9/03 15804 5 1 7S131MPA011 4/14/03 15809 2 1 7S131MPA011 4/14/03 15809 2 1 7S131MPA008 4/16/03 15811 30 1 7S131MPA010 5/16/03 15841 64 2 7S131MPA011 7/19/03 15905 8 2 7S131MPA008 7/27/03 15913 1 2 7S131MPA011 7/27/03 15913 1 3 7S131MPA010 7/28/03 15914 1 4 7S131MPA008 7/29/03 15915 1 5 7S131MPA008 7/30/03 15916 14 8 7S131MPA011 8/13/03 15930 3 14 7S131MPA008 8/16/03 15933 31 22 7S131MPA010 8/16/03 15933 31 30 7S131MPA010 9/16/03 15964 22 31 7S131MPA011 10/8/03 15986 132 31 7S132MPA009 2/17/04 16118 4 64 7S132MPA009 2/21/04 16122 2 132 7S131MPA008 2/23/04 16124
Table1
420
TPNS CreatedTS date time Group2
7S132TFW0519 5/14/2003 15839 15 1 7S132TFW0519 5/14/2003 15839 15 1 7S132TFW0003 5/29/2003 15854 30 1 7S132TFW0239 6/28/2003 15884 29 2 7S131TFW0057 7/27/2003 15913 5 2 7S131TFW0516 7/27/2003 15913 5 2 7S131TFW0068 8/1/2003 15918 1 2 7S131TFW0109 8/1/2003 15918 1 2 7S131TFW0476 8/1/2003 15918 1 5 7S131TFW0042 8/2/2003 15919 2 5 7S131TFW0093 8/2/2003 15919 2 5 7S131TFW0109 8/2/2003 15919 2 8 7S131TFW0194 8/2/2003 15919 2 8 7S131TFW0272 8/2/2003 15919 2 15 7S131TFW0190 8/4/2003 15921 5 15 7S131TFW0061 8/9/2003 15926 77 16 7S131TFW0054 10/25/2003 16003 16 18 7S131TFW0200 11/10/2003 16019 8 23 7S131TFW0107 11/18/2003 16027 23 29 7S131TFW0193 12/11/2003 16050 18 30 7S132TFW0065 12/29/2003 16068 8 77 7S132TFW0190 1/6/2004 16076
Table2
TPNS CreatedTS date time Group3
7T081MPA001A 4/5/2003 15800 21 1 7T081MPA1803 4/26/2003 15821 59 2 7T082MPA1803 4/26/2003 15821 59 9 7T082MPA001B 6/24/2003 15880 30 12 7T081MPA001A 7/24/2003 15910 2 21 7T081MPA001A 7/26/2003 15912 12 30 7T082MPA1803 8/7/2003 15924 1 59 7T081MPA001A 8/8/2003 15925 9 59 7T082MPA1803 8/17/2003 15934 178 178 7T081MPA001A 2/11/2004 16112 7T081MPA001A 2/11/2004 16112
Table3
421
TPNS CreatedTS date time Group 4
7T082MRC003A 1/23/1995 12806 91 2 7T081MRC004B 4/24/1995 12897 331 3 7T081MRC003B 3/20/1996 13228 48 3 7T081MRC004B 3/20/1996 13228 48 27 7T081MRC005B 3/20/1996 13228 48 37 7T081MRC005A 5/7/1996 13276 37 41 7T081MRC003A 6/13/1996 13313 63 41 7T082MRC003A 8/15/1996 13376 41 47 7T082MRC004B 9/25/1996 13417 499 48 7T082MRC005B 9/25/1996 13417 499 48 7T081MRC005B 2/6/1998 13916 332 48 7T082MRC005B 1/4/1999 14248 47 49 7T082MRC003B 2/20/1999 14295 319 50 7T082MRC004B 1/5/2000 14614 27 50 7T082MRC003B 2/1/2000 14641 50 57 7T082MRC004B 3/22/2000 14691 50 63 7T081MRC004B 5/11/2000 14741 255 91 7T081MRC004B 1/21/2001 14996 669 255 7T082MRC004B 11/21/2002 15665 2 319 7T082MRC005B 11/23/2002 15667 57 331 7T082MRC003B 1/19/2003 15724 3 332 7T082MRC005B 1/19/2003 15724 3 499 7T082MRC005B 1/22/2003 15727 49 499 7T082MRC005B 3/12/2003 15776 41 669 7T081MRC004B 4/22/2003 15817 7T081MRC004B 4/22/2003 15817
Table4
422
TPNS CreatedTS date time Group5 7T082XEH0006 3/2/1995 12844 396 4 7T081XEH0169 4/1/1996 13240 71 8 7T081XEH0002 6/11/1996 13311 8 10 7T082XEH0099 6/19/1996 13319 72 12 7T082XEH0156 6/19/1996 13319 72 19 7T082XEH0164 6/19/1996 13319 72 20 7T081XEH0011 8/30/1996 13391 26 26 7T082XEH0164 9/25/1996 13417 12 29 7T082XEH0007 10/7/1996 13429 181 39 7T082XEH0011 10/7/1996 13429 181 39 7T081XEH0095 4/6/1997 13610 84 41 7T081XEH0161 4/6/1997 13610 84 71 7T081XEH0154 6/29/1997 13694 667 72 7T081XEH0162 4/27/1999 14361 139 72 7T081XEH0167 9/13/1999 14500 29 72 7T082XEH0001 10/12/1999 14529 211 84 7T081XEH0154 5/10/2000 14740 308 84 7T081XEH0004 3/14/2001 15048 19 88 7T082XEH0006 4/2/2001 15067 10 92 7T082XEH0011 4/12/2001 15077 88 92 7T081XEH0003 7/9/2001 15165 92 92 7T081XEH0003 7/9/2001 15165 92 92 7T081XEH0007 7/9/2001 15165 92 92 7T081XEH0007 7/9/2001 15165 92 92 7T081XEH0011 7/9/2001 15165 92 94 7T081XEH0011 7/9/2001 15165 92 106 7T082XEH0099 10/9/2001 15257 128 106 7T081XEH0011 2/14/2002 15385 4 128 7T081XEH0009 2/18/2002 15389 41 139 7T081XEH0011 3/31/2002 15430 235 181 7T082XEH0154 11/21/2002 15665 20 181 7T082XEH0002 12/11/2002 15685 39 188 7T082XEH0010 12/11/2002 15685 39 188 7T082XEH0154 1/19/2003 15724 94 211 7T082XEH0011 4/23/2003 15818 188 235 7T082XEH0011 4/23/2003 15818 188 308 7T082XEH0011 10/28/2003 16006 106 396 7T082XEH0011 10/28/2003 16006 106 667 7T081XEH0020 2/11/2004 16112 7T081XEH0020 2/11/2004 16112
Table5
423
TPNS CreatedTS date time Group6
8S102MTU0133 04/11/2003 15806 12 12 8S101MTU0133 04/23/2003 15818 36 36 8S101MTU0233 04/23/2003 15818 36 36 8S102MTU0333 05/29/2003 15854 75 57 8S101MTU0133 08/12/2003 15929 57 65 8S101MTU0133 10/08/2003 15986 68 68 8S101MTU0233 12/15/2003 16054 65 75 8S102MTU0233 02/18/2004 16119 8S102MTU0333 02/18/2004 16119
Table6
424
TPNS CreatedTS date time Group7 8S131MPA02 04/15/2003 15810 6 1 8S131MPA028 04/21/2003 15816 5 2 8S132MPA02 04/26/2003 15821 2 2 8S131MPA06 04/28/2003 15823 3 2 8S131MPA01 05/01/2003 15826 2 2 8S132MPA02 05/03/2003 15828 1 2 8S132MPA028 05/04/2003 15829 6 2 8S131MPA01 05/10/2003 15835 22 2 8S131MPA11 06/01/2003 15857 15 2 8S131MPA007 06/16/2003 15872 12 3 8S131MPA007 06/28/2003 15884 27 3 8S131MPA028 07/25/2003 15911 10 3 8S132MPA007 07/25/2003 15911 10 5 8S131MPA007 08/04/2003 15921 2 5 8S131MPA05 08/04/2003 15921 2 6 8S131MPA05 08/06/2003 15923 2 6 8S131MPA05 08/06/2003 15923 2 8 8S131MPA12 08/06/2003 15923 2 8 8S131MPA02 08/08/2003 15925 2 8 8S131MPA02 08/10/2003 15927 16 8 8S131MPA11 08/26/2003 15943 3 8 8S131MPA11 08/29/2003 15946 8 8 8S131MPA11 09/06/2003 15954 5 8 8S131MPA11 09/11/2003 15959 8 10 8S131MPA03 09/19/2003 15967 11 10 8S131MPA02 09/30/2003 15978 58 11 8S131MPA05 11/27/2003 16036 11 11 8S131MPA01 12/08/2003 16047 15 12 8S131MPA02 12/08/2003 16047 15 13 8S131MPA03 12/23/2003 16062 3 15 8S132MPA13 12/26/2003 16065 32 15 8S131MPA04 01/27/2004 16097 8 15 8S132MPA04 02/04/2004 16105 8 16 8S132MPA04 02/04/2004 16105 8 22 8S132MPA05 02/04/2004 16105 8 27 8S132MPA05 02/04/2004 16105 8 32 8S132MPA03 02/12/2004 16113 13 58 8S131MPA01 02/25/2004 16126
Table 7
425
TPNS CreatedTS date time Group8 9S131ZLP609 10/13/1994 12704 385 1 9S131ZLP609 10/13/1994 12704 385 1 9S132ZLP609 11/02/1995 13089 2338 1 9S131ZLP609 03/28/2002 15427 82 1 9S131ZLP609 03/28/2002 15427 82 82 9S132ZLP609 06/18/2002 15509 166 82 9S132ZLP609 12/01/2002 15675 161 94 9S132ZLP145 05/11/2003 15836 94 161 9S131ZLP609 08/13/2003 15930 166 166 9S131ZLP609 08/13/2003 15930 166 166 9S131ZLP609 01/26/2004 16096 1 166 9S131ZLP609 01/26/2004 16096 1 385 9S131ZLP609A 01/26/2004 16096 1 385 9S131ZLP609A 01/26/2004 16096 1 2338 9S131ZLP609 01/27/2004 16097 9S132ZLP609 01/27/2004 16097
Table 8
TPNS CreatedTS date time Group9 A1FWFV7143 04/22/2003 15817 40 3 A1FWFV7141 06/01/2003 15857 9 5 A2FWFV7142 06/10/2003 15866 13 7 A2FWFV7141 06/23/2003 15879 26 7 A2FWFV7143 06/23/2003 15879 26 7 A1FWFV7142 07/19/2003 15905 3 7 A1FWFV7141 07/22/2003 15908 7 8 A2FWFV7141 07/22/2003 15908 7 8 A2FWFV7142 07/22/2003 15908 7 9 A2FWFV7143 07/22/2003 15908 7 13 A1FWFV7141 07/29/2003 15915 5 15 A1FWFV7142 08/03/2003 15920 8 15 A1FWFV7147A 08/03/2003 15920 8 26 A1FWFV7141 08/11/2003 15928 73 26 A2FWFV7147A 10/23/2003 16001 30 30 A2FWFV7147A 10/23/2003 16001 30 30 A1FWFV7141 11/22/2003 16031 15 40 A1FWFV7143 11/22/2003 16031 15 73 A1FWFV7143 12/07/2003 16046
Table 9
426
TPNS CreatedTS date time Group10 N2FWFCV0554 04/02/2003 15797 2 2 N1FWFCV0551 04/04/2003 15799 4 4 N1FWFCV0552 04/04/2003 15799 4 4 N2FWFCV0551 04/04/2003 15799 4 4 N2FWFCV0552 04/04/2003 15799 4 4 N2FWFCV0553 04/04/2003 15799 4 4 N2FWFCV0553 04/08/2003 15803 5 4 N2FWFCV0551 04/13/2003 15808 20 4 N2FWFCV0552 05/03/2003 15828 138 5 N1FWFCV0551 09/18/2003 15966 4 20 N1FWFCV0554 09/18/2003 15966 4 124 N1FWFCV0551 09/22/2003 15970 124 124 N1FWFCV0552 09/22/2003 15970 124 124 N1FWFCV0553 09/22/2003 15970 124 124 N2FWFCV0551 09/22/2003 15970 124 124 N2FWFCV0552 09/22/2003 15970 124 124 N2FWFCV0553 09/22/2003 15970 124 124 N2FWFCV0554 09/22/2003 15970 124 138 N1FWFCV0552 01/24/2004 16094
Table 10
427
TPNS CreatedTS date time Group11 N1FWFV7109 04/03/2003 15798 1 1 N1FWFV7151 04/04/2003 15799 3 1 N1FWFV7152 04/04/2003 15799 3 1 N1FWFV7153 04/04/2003 15799 3 2 N2FWFV7151 04/04/2003 15799 3 3 N2FWFV7152 04/04/2003 15799 3 3 N2FWFV7154 04/04/2003 15799 3 3 N1FWFV7154 04/07/2003 15802 2 3 N1FWFV7153 04/09/2003 15804 6 3 N1FWFV7151 04/15/2003 15810 1 3 N1FWFV7177 04/15/2003 15810 1 6 N1FWFV7104 04/16/2003 15811 6 6 N1FWFV7114 04/16/2003 15811 6 6 N1FWFV7114 04/16/2003 15811 6 6 N1FWFV7178 04/22/2003 15817 8 8 N2FWFV7109 04/30/2003 15825 82 13 N2FWFV7114 04/30/2003 15825 82 16 N2FWFV7104 07/21/2003 15907 16 16 N2FWFV7109 07/21/2003 15907 16 16 N2FWFV7114 07/21/2003 15907 16 24 N1FWFV7114 08/06/2003 15923 35 24 N1FWFV7177 09/10/2003 15958 13 35 N2FWFV7153 09/23/2003 15971 45 45 N1FWFV7154 11/07/2003 16016 86 82 N2FWFV7176 02/01/2004 16102 24 82 N2FWFV7178 02/01/2004 16102 24 86 N1FWFV7109 02/25/2004 16126
428
III. Data tables for code assignment and failure modes TPNS Created TS Failure_Mode code date Group1 7T081XEH0011 8/30/1996 4:50 AOV-LE-C 451 35307 39 7T082XEH0007 10/7/1996 AOV-LE-C 451 35346 1619 7T081XEH0004 3/14/2001 10:11 AOV-LE-C 451 36964 29 7T082XEH0011 4/12/2001 AOV-LE-C 451 36993 308 7T081XEH0011 2/14/2002 4:32 AOV-LE-C 451 37301 45 7T081XEH0011 3/31/2002 8:40 AOV-LE-C 451 37346 388 7T082XEH0011 4/23/2003 AOV-LE-C 451 37735 188 7T082XEH0011 4/23/2003 AOV-LE-C 451 37735 188 7T082XEH0011 10/28/2003 AOV-LE-C 451 37922 7T082XEH0011 10/28/2003 AOV-LE-C 451 37922
Table1 TPNS Created TS Failure_Mode code date Group2 7T081MRC004B 4/24/1995 8:04 TKP-LE-C 455 34813 331 7T081MRC003B 3/20/1996 8:13 TKP-LE-C 455 35144 189 7T081MRC004B 3/20/1996 8:13 TKP-LE-C 455 35144 189 7T081MRC005B 3/20/1996 8:13 TKP-LE-C 455 35144 189 7T082MRC005B 9/25/1996 TKP-LE-C 455 35333 499 7T081MRC005B 2/6/1998 10:37 TKP-LE-C 455 35832 333 7T082MRC005B 1/4/1999 TKP-LE-C 455 36165 46 7T082MRC003B 2/20/1999 TKP-LE-C 455 36211 347 7T082MRC003B 2/1/2000 TKP-LE-C 455 36558 50 7T082MRC004B 3/22/2000 TKP-LE-C 455 36608 50 7T081MRC004B 5/11/2000 10:11 TKP-LE-C 455 36657 255 7T081MRC004B 1/21/2001 11:18 TKP-LE-C 455 36912 669 7T082MRC004B 11/21/2002 TKP-LE-C 455 37582 2 7T082MRC005B 11/23/2002 TKP-LE-C 455 37583 57 7T082MRC005B 1/19/2003 TKP-LE-C 455 37640 3 7T082MRC003B 1/19/2003 TKP-LE-C 455 37640 3 7T082MRC005B 1/22/2003 TKP-LE-C 455 37644 49 7T082MRC005B 3/12/2003 TKP-LE-C 455 37692 41 7T081MRC004B 4/22/2003 17:25 TKP-LE-C 455 37734 7T081MRC004B 4/22/2003 17:25 TKP-LE-C 455 37734
Table 2
429
TPNS Created TS Failure_Mode code date Group3
A1FWFV7143 4/22/2003
14:47 XVM-LE-W 92 37734 40 A1FWFV7141 6/1/2003 13:25 XVM-LE-W 92 37774 48
A1FWFV7142 7/19/2003
16:38 XVM-LE-W 92 37822 3
A1FWFV7141 7/22/2003
21:28 XVM-LE-W 92 37825 7
A1FWFV7141 7/29/2003
23:47 XVM-LE-W 92 37832 13
A1FWFV7141 8/11/2003
14:56 XVM-LE-W 92 37845 102
A1FWFV7141 11/22/2003
1:21 XVM-LE-W 92 37947 213
A1FWFV7143 11/22/2003
1:25 XVM-LE-W 92 37947 1358202565 Table3
TPNS Created TS Failure_Mode code date Group4 N2FWFCV0554 4/2/2003 CAV-LE-W 95 37713 3 N1FWFCV0551 4/4/2003 15:45 CAV-LE-W 95 37716 4 N1FWFCV0552 4/4/2003 15:45 CAV-LE-W 95 37716 4 N2FWFCV0551 4/4/2003 CAV-LE-W 95 37716 4 N2FWFCV0552 4/4/2003 CAV-LE-W 95 37716 4 N2FWFCV0553 4/4/2003 CAV-LE-W 95 37716 4 N2FWFCV0553 4/8/2003 CAV-LE-W 95 37720 4 N2FWFCV0551 4/13/2003 CAV-LE-W 95 37724 20 N2FWFCV0552 5/3/2003 CAV-LE-W 95 37744 138 N1FWFCV0554 9/18/2003 4:03 CAV-LE-W 95 37882 4 N1FWFCV0551 9/18/2003 4:05 CAV-LE-W 95 37882 4
N1FWFCV0551 9/22/2003
10:14 CAV-LE-W 95 37886
N1FWFCV0552 9/22/2003
10:14 CAV-LE-W 95 37886
N1FWFCV0553 9/22/2003
10:14 CAV-LE-W 95 37886 N2FWFCV0552 9/22/2003 CAV-LE-W 95 37886 N2FWFCV0553 9/22/2003 CAV-LE-W 95 37886 N2FWFCV0554 9/22/2003 CAV-LE-W 95 37886
Table4
430
TPNS Created TS Failure_Mode code date Group5 N1FWFV7151 4/4/2003 15:45 CAV-LE-W 96 37716 2 N1FWFV7152 4/4/2003 15:45 CAV-LE-W 96 37716 2 N1FWFV7153 4/4/2003 15:45 CAV-LE-W 96 37716 2 N2FWFV7151 4/4/2003 CAV-LE-W 96 37716 2 N2FWFV7152 4/4/2003 CAV-LE-W 96 37716 2 N2FWFV7154 4/4/2003 CAV-LE-W 96 37716 2 N1FWFV7154 4/7/2003 9:02 CAV-LE-W 96 37718 3 N1FWFV7153 4/9/2003 20:23 CAV-LE-W 96 37721 166 N2FWFV7153 9/23/2003 CAV-LE-W 96 37887 45 N1FWFV7154 11/7/2003 2:56 CAV-LE-W 96 37932
Table5 Created TS Failure_Mode code date Group6
4/16/2003 14:12 MDP-LE-C 127 37728 30 5/16/2003 13:42 MDP-LE-C 127 37758 72 7/27/2003 3:46 MDP-LE-C 127 37829 1
7/28/2003 10:18 MDP-LE-C 127 37830 1 7/29/2003 3:24 MDP-LE-C 127 37831 15 8/13/2003 5:42 MDP-LE-C 127 37846 4
8/16/2003 22:41 MDP-LE-C 127 37850 30 8/16/2003 22:44 MDP-LE-C 127 37850 30 9/16/2003 9:53 MDP-LE-C 127 37880 22
10/8/2003 12:47 MDP-LE-C 127 37903 138
02/23/04 10:00 PM MDP-LE-C 127 38041 Table6
431
IV. Histograms for Functional Grouping
group1
Freq
uenc
y
140120100806040200
40
30
20
10
0
Shape 0.6793Scale 15.39N 17
Histogram for Group1
Funtional Grouping
Weibull
Figure1
group2
Freq
uenc
y
806040200
25
20
15
10
5
0
Shape 0.8332Scale 11.39N 21
Histogram for Group2
Funtional Grouping
Weibull
Figure2
432
group3
Freq
uenc
y
250200150100500
10
8
6
4
2
0
Shape 0.7536Scale 34.65N 9
histigram for Group3
Functional Grouping
Weibull
Figure 3
group4
Freq
uenc
y
8006004002000
30
25
20
15
10
5
0
Shape 0.7677Scale 128.0N 24
Histogram for Group4
Funtional Grouping
Weibull
Figure4
433
group5
Freq
uenc
y
6404803201600
20
15
10
5
0
Shape 1.069Scale 121.0N 38
Histogram for Group5
Funtional Grouping
Weibull
Figure5
group6
Freq
uenc
y
100806040200
2.0
1.5
1.0
0.5
0.0
Shape 2.630Scale 55.98N 7
Histogram for Group6
Funtional Grouping
Weibull
Figure 6
434
group7
Freq
uenc
y
56484032241680
25
20
15
10
5
0
Shape 1.099Scale 10.44N 37
Histogram for Group7
Funtional Grouping
Weibull
Figure7
group8
Freq
uenc
y
300025002000150010005000
25
20
15
10
5
0
Shape 0.4987Scale 148.4N 14
Histogram for Group8
Funtional Grouping
Weibull
Figure8
435
group9
Freq
uenc
y
706050403020100
9
8
7
6
5
4
3
2
1
0
Shape 1.222Scale 19.68N 18
Histogram for Group9
Funtional Grouping
Weibull
Figure 9
group10
Freq
uenc
y
420360300240180120600
14
12
10
8
6
4
2
0
Shape 0.6787Scale 46.27N 18
Histogram for Group10
Funtional Grouping
Weibull
Figure 10
436
group11
Freq
uenc
y
100806040200
25
20
15
10
5
0
Shape 0.7726Scale 16.03N 26
Histogram for Group11
Funtional Grouping
Weibull
Figure 11
437
V. Histograms for Code and Failure Mode Grouping
group1
Freq
uenc
y
2000160012008004000
8
7
6
5
4
3
2
1
0
Shape 0.7902Scale 299.9N 8
Histogram for Group1
Code Assignment and Failure mode Grouping
Weibull
Figure 1
group2
Freq
uenc
y
10008006004002000
18
16
14
12
10
8
6
4
2
0
Shape 0.7896Scale 163.2N 18
Histogram for Group2
Code Assignment and Failure mode Grouping
Weibull
Figure 2
438
group3
Freq
uenc
y
16012080400
4
3
2
1
0
Shape 0.9693Scale 35.01N 6
Histogram for Group3
Code Assignment and Failure mode Grouping
Weibull
Figure 3
group4
Freq
uenc
y
140120100806040200
30
25
20
15
10
5
0
Shape 0.6793Scale 11.76N 11
Histogram for Group4
Code Assignment and Failure mode Grouping
Weibull
Figure 4
439
group5
Freq
uenc
y
20016012080400
20
15
10
5
0
Shape 0.5336Scale 11.68N 9
Histogram for Group5
Code Assignment and Failure mode Grouping
Weibull
Figure 5
group6
Freq
uenc
y
20016012080400
10
8
6
4
2
0
Shape 0.7873Scale 30.08N 10
Histogram for Group6
Code Assignment and Failure mode Grouping
Weibull
Figure 6
440
VI. Probability Plots for Functional Grouping
group1
Perc
ent
1000.000100.00010.0001.0000.1000.0100.001
95
80
50
20
5
2
1
Shape
0.144
0.6793Scale 15.39N 1AD 0.562P-Value
Probability Plot for Group1
Functional Grouping
Weibull - 90% CI
7
Figure 1
group2
Perc
ent
100.0010.001.000.100.01
99
90807060504030
20
10
5
3
2
1
Shape
0.158
0.8332Scale 11.39N 2AD 0.550P-Value
Probability Plot for Group2
Functional Grouping
Weibull - 90% CI
1
Figure2
441
group3
Perc
ent
1000.000100.00010.0001.0000.1000.0100.001
99
90807060504030
20
10
5
3
2
1
Shape
>0.250
0.7536Scale 34.65N 9AD 0.172P-Value
Probability Plot for Group3
Functional Grouping
Weibull - 90% CI
Figure3
group4
Perc
ent
1000.0100.010.01.00.1
99
90807060504030
20
10
5
3
2
1
Shape
<0.010
0.7677Scale 128.0N 2AD 1.209P-Value
Probability Plot for Group4
Functional Grouping
Weibull - 90% CI
4
Figure 4
442
group5
Perc
ent
1000100101
99
90807060504030
20
10
5
3
2
1
Shape
0.115
1.069Scale 121.0N 38AD 0.601P-Value
Probability Plot for Group5
Functional Grouping
Weibull - 90% CI
Figure 5
group6
Perc
ent
10010
99
90807060504030
20
10
5
3
2
1
Shape
0.233
2.630Scale 55.98N 7AD 0.458P-Value
Probability Plot for Group6
Functional Grouping
Weibull - 90% CI
Figure 6
443
group7
Perc
ent
100.010.01.00.1
99
90807060504030
20
10
5
3
2
1
Shape
0.045
1.099Scale 10.44N 37AD 0.756P-Value
Probability Plot for Group7
Functional Grouping
Weibull - 90% CI
Figure7
group8
Perc
ent
1000
0.00
00
1000
.000
0
100.00
00
10.000
0
1.00
00
0.10
00
0.01
00
0.00
10
0.00
01
99
90807060504030
20
10
5
32
1
Shape
0.016
0.4987Scale 148.4N 1AD 0.922P-Value
Probability Plot for Group8
Functional Grouping
Weibull - 90% CI
4
Figure 8
444
group9
Perc
ent
100.010.01.00.1
99
90807060504030
20
10
5
3
2
1
Shape
0.069
1.222Scale 19.68N 18AD 0.680P-Value
Probability Plot for Group9
Functional Grouping
Weibull - 90% CI
Figure 9
group10
Perc
ent
1000.000100.00010.0001.0000.1000.0100.001
99
90807060504030
20
10
5
3
2
1
Shape
<0.010
0.6787Scale 46.27N 1AD 2.481P-Value
Probability Plot for Group10
Functional Grouping
Weibull - 90% CI
8
Figure 10
445
group11
Perc
ent
100.0010.001.000.100.01
99
90807060504030
20
10
5
3
2
1
Shape
0.042
0.7726Scale 16.03N 2AD 0.765P-Value
Probability Plot for Group11
Functional Grouping
Weibull - 90% CI
6
Figure 11
446
VII. Probability Plots for Code Assignment and Failure Mode Grouping
group1
Perc
ent
10000.01000.0100.010.01.00.1
99
90807060504030
20
10
5
3
2
1
Shape
>0.250
0.7902Scale 299.9N 8AD 0.380P-Value
Probability Plot for Group1
Code Assignment and failure mode Grouping
Weibull - 90% CI
Figure 1
group2
Perc
ent
10000.01000.0100.010.01.00.1
99
90807060504030
20
10
5
3
2
1
Shape
0.102
0.7896Scale 163.2N 1AD 0.606P-Value
Probability Plot for Group2
Code Assignment and failure mode Grouping
Weibull - 90% CI
8
Figure 2
447
group3
Perc
ent
1000.00100.0010.001.000.100.01
99
90807060504030
20
10
5
3
2
1
Shape
>0.250
0.9693Scale 35.01N 6AD 0.229P-Value
Probability Plot for Group3
Code Assignment and failure mode Grouping
Weibull - 90% CI
Figure 3
group4
Perc
ent
1000.000100.00010.0001.0000.1000.0100.001
99
90807060504030
20
10
5
3
2
1
Shape
<0.010
0.6793Scale 11.76N 1AD 2.412P-Value
Probability Plot for Group4
Code Assignment and failure mode Grouping
Weibull - 90% CI
1
Figure 4
448
group5
Perc
ent
1000
.000
00
100.00
000
10.000
00
1.00
000
0.10
000
0.01
000
0.00
100
0.00
010
0.00
001
99
90807060504030
20
10
5
32
1
Shape
<0.010
0.5336Scale 11.68N 9AD 1.696P-Value
Probability Plot for Group5
Code Assignment and failure mode Grouping
Weibull - 90% CI
Figure 5
group6
Perc
ent
1000.00100.0010.001.000.100.01
99
90807060504030
20
10
5
3
2
1
Shape
>0.250
0.7873Scale 30.08N 1AD 0.359P-Value
Probability Plot for Group6
Code Assignment and failure mode Grouping
Weibull - 90% CI
0
Figure6
449